Scenario Command

elizaos scenario <subcommand> [options]

elizaos scenario run <filePath> [options]

# Run a scenario
elizaos scenario run ./tests/greeting.scenario.yaml

# Run in live mode (no mocking)
elizaos scenario run ./tests/api-test.scenario.yaml --live

elizaos scenario matrix <configPath> [options]

# Analyze matrix without executing
elizaos scenario matrix ./matrix-config.yaml --dry-run

# Execute matrix with parallel runs
elizaos scenario matrix ./matrix-config.yaml --parallel 4

# Filter specific combinations
elizaos scenario matrix ./matrix-config.yaml --filter "model=gpt-4"

# Verbose execution
elizaos scenario matrix ./matrix-config.yaml --verbose

name: greeting-test
description: Test agent greeting behavior

setup:
  mocks:
    - type: llm
      response: "Hello! How can I help you today?"

run:
  - action: send_message
    content: "Hello"
    evaluations:
      - type: string_contains
        value: "Hello"

judgment:
  strategy: all_pass

name: model-comparison
description: Compare agent behavior across models

base_scenario: ./base.scenario.yaml
runs_per_combination: 3

matrix:
  - parameter: setup.mocks[0].model
    values:
      - gpt-4
      - gpt-3.5-turbo
      - claude-3-opus

  - parameter: run[0].content
    values:
      - "Hello"
      - "Hi there"
      - "Good morning"

_logs_/
├── run-001-execution-0.json    # Execution result step 0
├── run-001-evaluation-0.json   # Evaluation result step 0
├── run-001.json                # Centralized run result
└── matrix-YYYYMMDD-HHMM/       # Matrix run output
    ├── run-001.json
    ├── run-002.json
    └── ...

setup:
  mocks:
    - type: llm
      model: gpt-4
      response: "Mocked response"

    - type: action
      name: SEND_MESSAGE
      result:
        success: true
        message: "Mocked action result"

plugins:
  - @elizaos/plugin-bootstrap
  - @elizaos/plugin-sql
  - name: @elizaos/plugin-discord
    enabled: false  # Disable specific plugin